Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 43268
    Prev
    Next
    INDEX
    Explanations

    terms related to lichens and undead creatures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    71
    +0.12
    0.5%
    285
    +0.10
    0.4%
    353
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.12
    0.01
    659
    +0.10
    0.01
    326
    +0.09
    0.01
    Negative Logits
    byss
    -0.89
     Samoa
    -0.78
     [|
    -0.67
     Kenyan
    -0.63
    xit
    -0.63
    LV
    -0.63
    yss
    -0.62
     Shinra
    -0.61
    qua
    -0.61
    mble
    -0.61
    POSITIVE LOGITS
    ucky
    1.09
    kamp
    0.97
    uation
    0.89
    lich
    0.83
    atures
    0.82
    ting
    0.81
    mann
    0.81
    uates
    0.79
    ty
    0.77
    uate
    0.77
    Activations Density 0.006%

    No Known Activations